© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60666
    Prev
    Next
    INDEX
    Explanations

    escape characters and slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    涨äºĨ
    -0.07
     lÃŃqu
    -0.07
    @email
    -0.07
    lik
    -0.07
    åħ¥åº§
    -0.07
    EAU
    -0.06
    æ©Ħæ¦Ħ
    -0.06
    秧
    -0.06
    æ²¹çĽIJ
    -0.06
     Body
    -0.06
    POSITIVE LOGITS
    .Magic
    0.08
     пиÑĪ
    0.07
    itou
    0.07
    azard
    0.07
    åħĭ森
    0.07
    onest
    0.07
    slash
    0.06
    èIJ¨æĸ¯
    0.06
    _blend
    0.06
     Marino
    0.06
    Activations Density 0.024%

    No Known Activations